Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Methods/Maxout

Maxout

GeneralIntroduced 200050 papers

Description

The Maxout Unit is a generalization of the ReLU and the leaky ReLU functions. It is a piecewise linear function that returns the maximum of the inputs, designed to be used in conjunction with dropout. Both ReLU and leaky ReLU are special cases of Maxout.

$f\left(x\right) = \max\left(w^{T}\_{1}x + b\_{1}, w^{T}\_{2}x + b\_{2}\right)$

The main drawback of Maxout is that it is computationally expensive as it doubles the number of parameters for each neuron.

Papers Using This Method

Deep-ICE: The first globally optimal algorithm for empirical risk minimization of two-layer maxout and ReLU networks2025-05-09 Depth-Bounds for Neural Networks via the Braid Arrangement2025-02-13 Deep Maxout Network-based Feature Fusion and Political Tangent Search Optimizer enabled Transfer Learning for Thalassemia Detection2023-08-03 Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs2023-05-23 Error bounds for maxout neural network approximations of model predictive control2023-04-18 Expected Gradients of Maxout Networks and Consequences to Parameter Initialization2023-01-17 Deep Maxout Network Gaussian Process2022-08-08 On the Number of Regions of Piecewise Linear Neural Networks2022-06-17 Learning with Stochastic Orders2022-05-27 Smooth Maximum Unit: Smooth Activation Function for Deep Networks Using Smoothing Maximum Technique2022-01-01 Learning Discriminative Shrinkage Deep Networks for Image Deconvolution2021-11-27 Time-Frequency Localization Using Deep Convolutional Maxout Neural Network in Persian Speech Recognition2021-08-09 On the Expected Complexity of Maxout Networks2021-07-01 Revisiting 2D Convolutional Neural Networks for Graph-based Applications2021-05-23 Maximum and Leaky Maximum Propagation2021-05-21 Performance Evaluation of Deep Convolutional Maxout Neural Network in Speech Recognition2021-05-04 Sharp bounds for the number of regions of maxout networks and vertices of Minkowski sums2021-04-16 A new semi-supervised self-training method for lung cancer prediction2020-12-17 Activate or Not: Learning Customized Activation2020-09-10 Deep Neural-Kernel Machines2020-07-13